observe-behavior
Exercise faithful behavioral surfaces, compare observation points, and calibrate evidence and claims during software exploration.
Skill by testobsessed
Chalk Labs
Need help deploying observe-behavior?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/testobsessed-observe-behavior
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/observe-behavior
What's inside
- Skill name
observe-behavior- Description
- Exercise faithful behavioral surfaces, compare observation points, and calibrate evidence and claims during software exploration.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- behavioral-evidence.md · references/
SKILL.md (first lines)
# Observing Behavior Use source code, documentation, and existing tests to orient, generate hypotheses, locate observation points, and explain established behavior. Do not treat source inspection alone as proof of runtime behavior when the behavior can reasonably be exercised. Prefer the user's exact artifact and action path before synthetic approximations. When an exact path is impractical, explain the fidelity gap. Compare multiple observation surfaces when possible: user interface, exported or persisted state, API results, domain objects, events, logs, metrics, and rendered summaries. Read [references/behavioral-evidence.md](references/behavioral-evidence.md) when choosing evidence, characterizing confidence, or reporting a finding. Record observations before interpreting them. Use exploratory-session-log unless the caller opts out; reuse the active session and guidance already loaded. Capture raw evidence promptly, indexing at closure or handoff. Standalone requests need only a proportionate raw record; create supporting records when useful. If the logger is unavailable, append dated evidence in the caller's workspace.
From testobsessed/exploratory-testing-skills, MIT.
More from testobsessed/exploratory-testing-skills
- 0.567score
exploratory-session-log
testobsessed
Record exploratory testing sessions with a charter first, append-only experiment and observation entries, and a final findings summary.
SkillAFreshness: AClaude Code +9 - 0.561score
explore-software
testobsessed
Coordinate adaptive, evidence-producing exploration around a charter.
SkillAFreshness: AClaude Code +9 - 0.561score
report-bugs
testobsessed
Write concise exploratory-testing bug reports for reliably reproducible specification violations or behavior obviously wrong in context.
SkillAFreshness: AClaude Code +9 - 0.561score
work-with-oracles
testobsessed
Find and assess fallible expectations and comparisons to judge observed software behavior and distinguish surprises from defects.
SkillAFreshness: AClaude Code +9 - 0.561score
charter-exploration
testobsessed
Break an exploratory testing mission into focused charters and revise their priorities as observations reveal new risks.
SkillAFreshness: AClaude Code +9 - 0.561score
design-experiments
testobsessed
Choose controlled variations and comparisons that answer exploratory questions, distinguish explanations, and investigate delayed behavior.
SkillAFreshness: AClaude Code +9 - 0.558score
log-exploration
testobsessed
Compatibility entry point for callers of the former exploration logger; use exploratory-session-log for new sessions.
SkillAFreshness: AClaude Code +9 - 0.558score
orient-to-software
testobsessed
Build initial software context through small behavioral probes when an exploratory agent is unfamiliar with the system.
SkillAFreshness: AClaude Code +9 - 0.556score
research-domain
testobsessed
Research user goals, domain terminology and rules, and common risks to inform software orientation and exploratory testing; reuse existing application…
SkillAFreshness: AClaude Code +9 - 0.553score
identify-variables
testobsessed
Identify conditions, values, states, and paths that could influence software behavior during exploratory testing.
SkillAFreshness: AClaude Code +9 - 0.553score
map-touch-points
testobsessed
Discover software entry points and connected places to control or observe behavior for an exploratory investigation.
SkillAFreshness: AClaude Code +9 - 0.553score
discover-invariants
testobsessed
Identify always and never expectations and their applicable scope when exploring software behavior.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 4, 2026 (27 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from testobsessed
- 0.567score
exploratory-session-log
testobsessed
Record exploratory testing sessions with a charter first, append-only experiment and observation entries, and a final findings summary.
SkillAFreshness: AClaude Code +9 - 0.561score
explore-software
testobsessed
Coordinate adaptive, evidence-producing exploration around a charter.
SkillAFreshness: AClaude Code +9 - 0.561score
report-bugs
testobsessed
Write concise exploratory-testing bug reports for reliably reproducible specification violations or behavior obviously wrong in context.
SkillAFreshness: AClaude Code +9 - 0.561score
work-with-oracles
testobsessed
Find and assess fallible expectations and comparisons to judge observed software behavior and distinguish surprises from defects.
SkillAFreshness: AClaude Code +9 - 0.561score
charter-exploration
testobsessed
Break an exploratory testing mission into focused charters and revise their priorities as observations reveal new risks.
SkillAFreshness: AClaude Code +9 - 0.561score
design-experiments
testobsessed
Choose controlled variations and comparisons that answer exploratory questions, distinguish explanations, and investigate delayed behavior.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get observe-behavior running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
observe-behavior skill. Agent Mart. https://agentmart.dev/skills/testobsessed-observe-behavior (last updated 2026-10-24)